CN105740237B - A kind of student ability degree of reaching evaluation measure based on Similarity of Words - Google Patents
A kind of student ability degree of reaching evaluation measure based on Similarity of Words Download PDFInfo
- Publication number
- CN105740237B CN105740237B CN201610076427.9A CN201610076427A CN105740237B CN 105740237 B CN105740237 B CN 105740237B CN 201610076427 A CN201610076427 A CN 201610076427A CN 105740237 B CN105740237 B CN 105740237B
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- index point
- examination
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000011156 evaluation Methods 0.000 title claims description 31
- 230000000694 effects Effects 0.000 claims abstract description 21
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 26
- 239000000284 extract Substances 0.000 claims description 5
- 102000003712 Complement factor B Human genes 0.000 claims description 4
- 108090000056 Complement factor B Proteins 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 238000003786 synthesis reaction Methods 0.000 claims description 4
- 238000013459 approach Methods 0.000 abstract description 6
- 239000002131 composite material Substances 0.000 abstract description 5
- 238000013507 mapping Methods 0.000 abstract description 4
- 238000005259 measurement Methods 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 238000004870 electrical engineering Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- RVRCFVVLDHTFFA-UHFFFAOYSA-N heptasodium;tungsten;nonatriacontahydrate Chemical compound O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.O.[Na+].[Na+].[Na+].[Na+].[Na+].[Na+].[Na+].[W].[W].[W].[W].[W].[W].[W].[W].[W].[W].[W] RVRCFVVLDHTFFA-UHFFFAOYSA-N 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Educational Technology (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of student ability degree of reaching based on Similarity of Words to evaluate measure, comprises the following steps:First by analyzing the coverage from examination examination question to requirements for graduation index point, the keyword of each examination paper and the corresponding graduation capacity index point of the course in paper is extracted respectively, forms keyword index list;Coverage factor of the examination content to its corresponding requirements for graduation index point is calculated in the semantic similarity calculation method for being then based on distance between vocabulary;Coverage factor and average achievement degree of reaching combined factors are obtained into the total factor of education activities degree of reaching again;Whether last set threshold value, judge index point are reached.Present invention employs mapping mechanism, realize mapping of the examination content to requirements for graduation index point, the ability that system is comprehensively reflected measurement reaches the composite factor of situation, can the relevant every factor of choosing comprehensively and student ability degree of reaching, fundamentally solve the problems of achievement analytic approach generally used now.
Description
Technical field
The present invention relates to a kind of student ability degree of reaching based on Similarity of Words to evaluate measure.
Background technology
In March, 2015, it is equivalent that the Ministry of Education releases international essence《Engineering Education Professional Certification Standards》, its core concept is
" output guiding " and " complex engineering problems " is directed toward.Engineering Education Professional Certification be operated in the whole nation respectively up to colleges and universities in high gear into
OK.
Existing Engineering Education Professional Certification scheme mostly using grade form analytic approach, Course Assessment achievement analytic approach and
The serial of methods such as questionnaire method, as shown in Figure 1, wherein Course Assessment achievement analytic approach only with average achievement as student
The measurement factor of ability degree of reaching, examination content is not set up and associated, react with the requirements for graduation index point for needing to examine
The coverage condition that examination content supports ability is not gone out.Obvious this scheme of achievement analytic approach is commented there is some evaluation loopholes
The reasonability of valency is difficult to be protected.Therefore the evaluation on student ability degree of reaching in Engineering Education Professional Certification need to be taken
One kind had not only considered student examination achievement, but also took into account the overall merit scheme for the coverage condition that examination content supports ability.
The content of the invention
In order to solve the above technical problem, the present invention provides a kind of scientific and reasonable, highly practical based on lexical semantic phase
Measure is evaluated like the student ability degree of reaching of degree.
Technical proposal that the invention solves the above-mentioned problems is:A kind of student ability degree of reaching based on Similarity of Words
Measure is evaluated, is comprised the following steps:
Step 1:Analysis examination examination question extracts in examination paper per problem the coverage of requirements for graduation index point respectively
The keyword of requirements for graduation index point corresponding to mesh and course corresponding with the examination paper, forms its respective keyword rope
Draw list;
Step 2:Keyword index list based on vocabulary spacing from metric calculation per pass exam question and each index point
Similarity, the similarity result for all examination paper and the index of adding up, takes smaller value by the result of gained compared with 1, that is, obtains
Coverage factor B of the examination paper to the index pointj;
Step 3:The education activities average achievement of all evaluation objects and the ratio of target achievement are calculated, it is A to make it, is obtained
Synthesis degree of reaching T to the education activities to index pointz=A × Bj;
Step 4:Weight coefficient matrix according to education activities to index point, by the weight corresponding to every subject and its
The product accumulation of coefficient, obtains degree of the reaching evaluation of estimate of the index point;
Step 5:Degree of the reaching evaluation of estimate threshold value of requirements for graduation index point is set, by the degree of reaching of the obtained index point
Evaluation of estimate is compared with threshold value, if degree of reaching evaluation of estimate is more than threshold value, then it is assumed that this requirements for graduation index point is reached, otherwise
Reach failure.
Above-mentioned student ability degree of the reaching evaluation measure based on Similarity of Words, the specific step of the step 2
Suddenly it is:
(1) per pass exam question and the similarity of the keyword index list of each index point are calculated;
The keyword index list M of exam question i in examination contentiSet of words is { Wi1, Wi2..., Win, graduation
It is required that the keyword index list S of index point jjSet of words is { Wj1, Wj2..., Wjm, thus obtain the similar of two lists
Spend matrix MiSjCalculation formula:
Wherein, Wi1Wj2For list MiMiddle word Wi1With list SjMiddle word Wj2Similarity, Wi1Wj2Calculation formula is as follows:
Wherein li, ljIt is Wi1Wj2Residing level respectively, Dis(Wi1, Wj2) distance between word, α is customized parameter,
0 < α < 1;
(2) maximal sequence value matrix maxM is calculatediSj;
Matrix M is taken firstiSjThe maximum MS of middle element1It is put into sequence maxMiSjIn, then by the row where this maximum
Deleted with row, form new matrix, maximum MS is further taken out in new matrix2It is placed on sequence maxMiSjIn MS1Afterwards, so
Circulation is sky up to matrix, obtains maximum value sequence maxMiSj:
naxMiSj={ MS1, MS2..., MSK};
(3) list M is obtainedi, SjSimilarity, i.e. coverage factor Sim (Mi, Sj);
Calculation formula is as follows:
Wherein len (Mi) it is list MiIn contained keyword number, len (Sj) it is list SjIn contained keyword
Number;
(4) by coverage factor Sim (Mi, Sj) and take smaller value compared with 1, this smaller value is examination content to finishing
Industry requires the coverage B of index pointj。
The beneficial effects of the present invention are:The present invention is first by analyzing from examination examination question covering to requirements for graduation index point
Cover degree, extracts the key for capacity index point of graduating in paper corresponding to each examination paper course corresponding with the examination paper respectively
Word, forms keyword index list, and examination content is calculated in the semantic similarity calculation method for being then based on distance between vocabulary
To the coverage factor of its corresponding requirements for graduation index point, finally by coverage factor and average achievement degree of reaching combined factors
Obtain the total factor of education activities degree of reaching;The present invention can the relevant every factor of choosing comprehensively and student ability degree of reaching,
The problems of achievement analytic approach generally used now is fundamentally solved, whole appraisement system employs mapping mechanism, realizes
Mapping of the examination content to requirements for graduation index point, the ability that system is comprehensively reflected measurement reach the composite factor of situation,
Scientific and reasonable, method is flexible, highly practical.
Brief description of the drawings
Fig. 1 is the flow chart of existing Engineering Education Professional Certification method.
Fig. 2 is the flow chart of the present invention.
Embodiment
The present invention is further illustrated with reference to the accompanying drawings and examples.
As shown in Fig. 2, a kind of student ability degree of reaching evaluation measure based on Similarity of Words, including it is following
Step:
Step 1:Analysis examination examination question extracts in examination paper per problem the coverage of requirements for graduation index point respectively
The keyword of requirements for graduation index point corresponding to mesh and course corresponding with the examination paper, forms its respective keyword rope
Draw list.
Step 2:Keyword index list based on vocabulary spacing from metric calculation per pass exam question and each index point
Similarity, the similarity result for all examination paper and the index of adding up, takes smaller value by the result of gained compared with 1, that is, obtains
Coverage factor B of the examination paper to the index pointj。
Step 2 concretely comprises the following steps:
(1) per pass exam question and the similarity of the keyword index list of each index point are calculated;
The keyword index list M of exam question i in examination contentiSet of words is { Wi1, Wi2..., Win, graduation
It is required that the keyword index list S of index point jjSet of words is { Wj1, Wj2..., Wjm, thus obtain the similar of two lists
Spend matrix MiSjCalculation formula:
Wherein, Wi1Wj2For list MiMiddle word Wi1With list SjMiddle word Wj2Similarity, Wi1Wj2Calculation formula is as follows:
Wherein li, ljIt is Wi1Wj2Residing level respectively, Dis (Wi1, Wj2) distance between word, α is adjustable ginseng
Number, 0 < α < 1;
(2) maximal sequence value matrix maxM is calculatediSj;
Matrix M is taken firstiSjThe maximum MS of middle element1It is put into sequence maxMiSjIn, then by the row where this maximum
Deleted with row, form new matrix, maximum MS is further taken out in new matrix2It is placed on sequence maxMiSjIn MS1Afterwards, so
Circulation is sky up to matrix, obtains maximum value sequence maxMiSj:
naxMiSj={ MS1,MS2,…,MSK};
(3) list M is obtainedi, SjSimilarity, i.e. coverage factor Sim (Mi, Sj);
Calculation formula is as follows:
Wherein len (Mi) it is list MiIn contained keyword number, len (Sj) it is list SjIn contained keyword
Number;
(4) by coverage factor Sim (Mi, Sj) and take smaller value compared with 1, this smaller value is examination content to finishing
Industry requires the coverage B of index pointj。
Specifically, based on vocabulary spacing from similarity calculating method establish exist《Chinese thesaurus》Language semantic knowledge
On dictionary.According to《Chinese thesaurus》In clump form tree, obtain between level and the vocabulary residing for two vocabulary
Distance.
Step 3:The education activities average achievement of all evaluation objects and the ratio of target achievement are calculated, it is A to make it, is obtained
Synthesis degree of reaching T to the education activities to index pointz=A × Bj;
Step 4:According to the synthesis degree of reaching of above-mentioned steps, according to this every subject corresponding to parameter point, according to teaching
Activity, by the product accumulation of the weight coefficient corresponding to every subject and its, obtains this and refers to the weight coefficient matrix of index point
Degree of the reaching evaluation of estimate of punctuate;
Step 5:Degree of the reaching evaluation of estimate threshold value of requirements for graduation index point is set, by the degree of reaching of the obtained index point
Evaluation of estimate is compared with threshold value, if degree of reaching evaluation of estimate is more than thresholding, then it is assumed that this requirements for graduation index point is reached, otherwise
Reach failure.
Specific embodiment
By the index point that each school formulates different majors for requirements for graduation, examination paper is all different, this reality
Example is applied with a branch of instruction in school of electrical engineering and it's automation major《The basic principles of Marxism》Exemplified by, illustrate present invention proposition
The ability that is included of the evaluation measure of the student ability degree of reaching based on Similarity of Words reach measurement pattern and energy
Power degree of reaching evaluation scheme.
Step 1:Analysis examination examination question extracts in examination paper per problem the coverage of requirements for graduation index point respectively
The keyword of requirements for graduation index point corresponding to mesh and course corresponding with the examination paper, forms its respective keyword rope
Draw list.
Requirements for graduation and examination content corresponding to course corresponding with the examination paper is as shown in table 1 below:
Table 1《The basic principles of Marxism》Index point and examination content
The keyword of index point 8.1 and 8.2 and exam question 1,2,3 obtains its keyword in extraction extraction table 1 respectively
Index list, as shown in table 2:
2 keyword index list of table
Index point | Lists of keywords |
S8.1(index point 8.1) | World outlook, outlook on life, meaning, influences |
S8.2(index point 8.2) | China, sustainable development, science are personal |
S12.2(index point 12.2) | Autonomous learning, importance, understanding |
M1(examination examination question 1) | World outlook, outlook on life, university student, meaning |
M2(examination examination question 2) | Science, country, productivity |
M3(examination examination question 3) | Sustainable development, university student is personal, ideal and faith |
Basis at the same time《Chinese thesaurus》Each list element is encoded, as shown in table 3:
3 keyword the encoding list of table
Index point | Lists of keywords |
S8.1(index point 8.1) | Df14, Df01, Db06, Je02 |
S8.2(index point 8.2) | Di02, Dd01, De04, Aa01 |
S12.2(index point 12.2) | Hg08, Ed28, Ga08 |
M1(examination examination question 1) | Df14, Df01, Ae13, Db06 |
M2(examination examination question 2) | De04, Di02, Dd14 |
M3(examination examination question 3) | Dd01, Ae13, Aa01, Df01 |
Step 2:Keyword index list based on vocabulary spacing from metric calculation per pass exam question and each index point
Similarity, the similarity result for all examination paper and the index of adding up, takes smaller value by the result of gained compared with 1, that is, obtains
Coverage factor B of the examination paper to the index pointj。
(1) according to the semantic similarity calculation method of distance between word-based, it is similar to each index point that each road examination paper are obtained
Spend matrix MiSj, it is as follows:
α=1/8,2/8,3/8 ... 8/8 is substituted into above-mentioned matrix respectively, by experiment with computing repeatedly, show that α=3/8 can be more
Reflect coverage situation exactly, therefore take α=3/8 to substitute into above-mentioned matrix MiSjIt can obtain:
(2) maximal sequence value matrix maxM is calculatediSj;
(3) list M is obtainedi, Sj| similarity, i.e. coverage factor Sim (Mi, Sj), and by coverage factor Sim (Mi,
Sj) and smaller value is taken compared with 1, this smaller value is coverage degree B of the examination content to requirements for graduation index pointj。
The coverage factor of index point 8.1 is summed, by summed result compared with 1 per problem according to examination paper
Take smaller value
Sim(M1, S8.1)+Sim(M2, S8.1)+Sim(M3, S8.1The > of)=1.77 1
Therefore the examination content is to the coverage B of index point 8.18.1For 1.
The coverage of index point 8.2 is summed per problem according to examination paper, summed result is taken compared with 1 compared with
Small value
Sim(M1, S8.2)+Sim(M2, S8.2)+Sim(M3, S8.2The > of)=1.89 1
Therefore the examination content is to the coverage B of index point 8.28.2For 1.
The coverage of index point 12.2 is summed per problem according to examination paper, summed result is taken compared with 1 compared with
Small value
Sim(M1, S12.2)+Sim(M2, S12.2)+Sim(M3, S12.3The < of)=0.883 1
Therefore the examination content is to the coverage B of index point 12.212.2For 0.883.
Step 3:The education activities average achievement of all evaluation objects and the ratio of target achievement are calculated, it is A to make it, is obtained
To the education activities to the comprehensive Delta of index point or degree Tz=A × Bj:
It is computed selected sample class《The basic principles of Marxism》The average achievement of this subject is 79 points, target
Achievement is 100 points, can obtain A=0.79.The education activities are understood through above-mentioned steps《The basic principles of Marxism》To index point
8.1 degree of reaching composite factor Tz:
Tz=A × B8.1
=0.79 × 1=0.79
The education activities《The basic principles of Marxism》Degree of reaching evaluation of estimate to index point 8.1 is 0.79.
Education activities《The basic principles of Marxism》To degree of the reaching composite factor T of index point 8.2z:
Tz=A × B8.2
=0.79 × 1=0.79
The education activities《The basic principles of Marxism》Degree of reaching evaluation of estimate to index point 8.2 is 0.79.
Education activities《The basic principles of Marxism》To degree of the reaching composite factor T of index point 12.2z:
Tz=A × B12.2
=0.79 × 0.883=0.6976
The education activities《The basic principles of Marxism》Degree of reaching evaluation of estimate to index point 12.2 is 0.6976.
Step 4:Weight coefficient matrix according to education activities to index point, by the weight corresponding to every subject and its
The product accumulation of coefficient, obtains degree of the reaching evaluation of estimate of the index point.
Education activities according to the electrical engineering and it's automation major can must support the weight coefficient matrix of index point
Three subjects of index point 8.1 are respectively《The basic principles of Marxism》,《Modern and Contemporary Chinese History outline》,《Chinese modern
Survey will》, its weight coefficient is respectively 0.3,0.4,0.3.Reaching for course corresponding to index point 8.1 can be drawn according to such scheme
It is as shown in table 4 into degree situation:
4 index point 8.1 of table reaches evaluation
Four subjects of support index point 8.2 are respectively《The basic principles of Marxism》,《Cultivation of Ethic Thought and law
Basis》,《Modern and Contemporary Chinese History outline》,《Social practice》Its weight coefficient is respectively 0.3,0.3,0.2,0.2.According to above-mentioned side
Case can show that degree of the reaching situation of course corresponding to index point 8.2 is as shown in table 5:
5 index point 8.2 of table reaches evaluation
Four subjects of support index point 12.2 are respectively《The basic principles of Marxism》,《University student's career development with
Careers guidance》,《Graduation project》,《College English》Its weight coefficient is respectively 0.3,0.3,0.2,0.2.Can according to such scheme
Show that degree of the reaching situation of course corresponding to index point 12.2 is as shown in table 6:
6 index point 12.2 of table reaches situation
Step 5:If requirements for graduation index point degree of the reaching threshold value of the major setting is 0.7, from the above results, finish
Industry life has been reached on the ability of index point 8.1,8.2, and then reaches failure on index point 12.2.
Claims (2)
1. a kind of student ability degree of reaching evaluation measure based on Similarity of Words, comprises the following steps:
Step 1:Analysis examination examination question to the coverage of requirements for graduation index point, extract respectively in examination paper per pass topic with
And the keyword of requirements for graduation index point corresponding to course corresponding with the examination paper, form its respective keyword index row
Table;
Step 2:Based on vocabulary spacing from metric calculation per pass exam question and the phase of the keyword index list of each index point
Like degree, add up all examination paper and the similarity result of the index, and the result of gained is taken smaller value compared with 1, that is, is taken an examination
Coverage factor B of the paper to the index pointj;
Step 3:The education activities average achievement of all evaluation objects and the ratio of target achievement are calculated, it is A to make it, is somebody's turn to do
Synthesis degree of reaching T of the education activities to index pointz=A × Bj;
Step 4:Weight coefficient matrix according to education activities to index point, by the weight coefficient corresponding to every subject and its
Product accumulation, obtain degree of the reaching evaluation of estimate of the index point;
Step 5:Degree of the reaching evaluation of estimate threshold value of requirements for graduation index point is set, the degree of reaching of the obtained index point is evaluated
Value is compared with threshold value, if degree of reaching evaluation of estimate is more than threshold value, then it is assumed that this requirements for graduation index point is reached, and otherwise reaches
Failure.
2. student ability degree of the reaching evaluation measure according to claim 1 based on Similarity of Words, it is special
Sign is:The step 2 concretely comprises the following steps:
(1) per pass exam question and the similarity of the keyword index list of each index point are calculated;
The keyword index list M of exam question i in examination contentiSet of words is { Wi1, Wi2..., Win, requirements for graduation
The keyword index list S of index point jjSet of words is { Wj1, Wj2..., Wjm, thus obtain the similarity moments of two lists
Battle array MiSjCalculation formula:
Wherein, Wi1Wj2For list MiMiddle word Wi1With list SjMiddle word Wj2Similarity, Wi1Wj2Calculation formula is as follows:
<mrow>
<msub>
<mi>W</mi>
<mrow>
<mi>i</mi>
<mn>1</mn>
</mrow>
</msub>
<msub>
<mi>W</mi>
<mrow>
<mi>j</mi>
<mn>2</mn>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mi>&alpha;</mi>
<mo>&times;</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>l</mi>
<mi>i</mi>
</msub>
<mo>+</mo>
<msub>
<mi>l</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mo>&lsqb;</mo>
<mi>D</mi>
<mi>i</mi>
<mi>s</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>i</mi>
<mn>1</mn>
</mrow>
</msub>
<mo>,</mo>
<msub>
<mi>W</mi>
<mrow>
<mi>j</mi>
<mn>2</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>&alpha;</mi>
<mo>&rsqb;</mo>
<mo>&times;</mo>
<mi>max</mi>
<mrow>
<mo>(</mo>
<mo>|</mo>
<mrow>
<msub>
<mi>l</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>l</mi>
<mi>j</mi>
</msub>
</mrow>
<mo>|</mo>
<mo>,</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
</mrow>
Wherein li, ljIt is Wi1Wj2Residing level respectively, Dis (Wi1, Wj2) distance between word, α is customized parameter, 0 < α
< 1;
(2) maximal sequence value matrix maxM is calculatediSj;
Matrix M is taken firstiSjThe maximum MS of middle element1It is put into sequence maxMiSjIn, then by the row and column where this maximum
Delete, form new matrix, maximum MS is further taken out in new matrix2It is placed on sequence maxMiSjIn MS1Afterwards, so circulation
Until matrix is sky, maximum value sequence maxM is obtainediSj:
maxMiSj={ MS1, MS2..., MSK};
(3) list M is obtainedi, SjSimilarity, i.e. coverage factor Sin (Mi, Sj);
Calculation formula is as follows:
<mrow>
<mi>S</mi>
<mi>i</mi>
<mi>m</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>M</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<msub>
<mi>S</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>max</mi>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mi>e</mi>
<mi>n</mi>
<mo>(</mo>
<msub>
<mi>S</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
<mo>,</mo>
<mi>l</mi>
<mi>e</mi>
<mi>n</mi>
<mo>(</mo>
<msub>
<mi>M</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<msubsup>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>k</mi>
</msubsup>
<msub>
<mi>MS</mi>
<mi>i</mi>
</msub>
</mrow>
Wherein len (Mi) it is list MiIn contained keyword number, len (Sj) it is list SjIn contained keyword number;
(4) by coverage factor Sim (Mi, Sj) and take smaller value compared with 1, this smaller value is that examination content will to graduation
Seek the coverage B of index pointj。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610076427.9A CN105740237B (en) | 2016-02-03 | 2016-02-03 | A kind of student ability degree of reaching evaluation measure based on Similarity of Words |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610076427.9A CN105740237B (en) | 2016-02-03 | 2016-02-03 | A kind of student ability degree of reaching evaluation measure based on Similarity of Words |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105740237A CN105740237A (en) | 2016-07-06 |
CN105740237B true CN105740237B (en) | 2018-04-13 |
Family
ID=56245820
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610076427.9A Expired - Fee Related CN105740237B (en) | 2016-02-03 | 2016-02-03 | A kind of student ability degree of reaching evaluation measure based on Similarity of Words |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105740237B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107169654A (en) * | 2017-05-12 | 2017-09-15 | 北京航空航天大学 | A kind of method and system for analyzing students'comprehensive ability |
CN109784710A (en) * | 2019-01-08 | 2019-05-21 | 上海大学 | A kind of higher education student's ability degree of reaching forming evaluation method based on quantitative calculating |
CN111461532A (en) * | 2020-03-30 | 2020-07-28 | 湘潭大学 | Student ability evaluation method based on intelligent vehicle competition |
CN111898928B (en) * | 2020-08-18 | 2021-08-31 | 哈尔滨工业大学 | Multi-party service value-quality-capability index alignment method facing space-time boundary |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6832069B2 (en) * | 2001-04-20 | 2004-12-14 | Educational Testing Service | Latent property diagnosing procedure |
KR20090058258A (en) * | 2007-12-04 | 2009-06-09 | 변두원 | Web-based analytic method of educational measurement and its system |
CN102354495B (en) * | 2011-08-31 | 2012-11-14 | 中国科学院自动化研究所 | Testing method and system of semi-opened spoken language examination questions |
CN102663555A (en) * | 2012-04-16 | 2012-09-12 | 苏州卫生职业技术学院 | Health evaluation objective structuralized clinical exam system and operation method thereof |
CN104346389A (en) * | 2013-08-01 | 2015-02-11 | 安徽科大讯飞信息科技股份有限公司 | Scoring method and system of semi-open-ended questions of oral test |
-
2016
- 2016-02-03 CN CN201610076427.9A patent/CN105740237B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN105740237A (en) | 2016-07-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107967254B (en) | Knowledge point prediction method and device, storage medium and electronic equipment | |
CN105740237B (en) | A kind of student ability degree of reaching evaluation measure based on Similarity of Words | |
CN106295796A (en) | Entity link method based on degree of depth study | |
CN105677822A (en) | Enrollment automatic question-answering method and system based on conversation robot | |
CN102662930A (en) | Corpus tagging method and corpus tagging device | |
CN106227718A (en) | Land based on CNN sky call semantic consistency method of calibration | |
CN104536881A (en) | Public testing error report priority sorting method based on natural language analysis | |
Maher et al. | Teaching master thesis writing to engineers: Insights from corpus and genre analysis of introductions | |
Gomaa et al. | Arabic short answer scoring with effective feedback for students | |
Malmi et al. | Automatic prediction of discourse connectives | |
Lomax | Introduction to structural equation modeling | |
Agarwal et al. | Autoeval: A nlp approach for automatic test evaluation system | |
Huaping et al. | ChatGPT performance evaluation on Chinese language and risk measures | |
Guo et al. | IJCNLP-2017 task 5: Multi-choice question answering in examinations | |
CN110895787A (en) | Method for dynamically matching English corpus difficulty and student ability analysis | |
Niu | Classification of learning sentiments of college students based on topic discussion texts of online learning platforms | |
Kusuma et al. | Automated essay scoring using machine learning | |
Chriqui et al. | Legal hebert: A bert-based nlp model for hebrew legal, judicial and legislative texts | |
Liu et al. | Design of adaptive learning system based on big data | |
Srihari et al. | Question and answer generation from text using transformers | |
CN105894408A (en) | Automation technology for scoring, rating, remarking, ranking and repetition elimination of composition on line | |
Huang et al. | RESEARCH ON INDEPENDENT COLLEGE TEACHERS’TEACHING ABILITY BASED ON FACTOR ANALYSIS IN SPSS | |
Kit et al. | Lexical need as a two-way reality cognition tool | |
Bayar et al. | The Colorado learning attitudes about science survey (CLASS): the study of validity and reliability | |
Kanerva et al. | Turkunlp: Delexicalized pre-training of word embeddings for dependency parsing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180413 Termination date: 20220203 |